• Journal of Korea Multimedia Society
• /
• v.14 no.12
• /
• pp.1544-1548
• /
• 2011

A process of choosing a subset of original features, so called feature selection, is considered as a crucial preprocessing step to image processing applications. There are already large pools of techniques developed for machine learning and data mining fields. In this paper, basically two methods, non-feature selection and feature selection, are investigated to compare their predictive effectiveness of classification. Color co-occurrence feature is used for defining image features. Standard Sequential Forward Selection algorithm are used for feature selection to identify relevant features and redundancy among relevant features. Four color spaces, RGB, YCbCr, HSV, and Gaussian space are considered for computing color co-occurrence features. Gray-level image feature is also considered for the performance comparison reasons. The experimental results are presented.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.34S no.1
• /
• pp.94-104
• /
• 1997

Most color imaging devices often exhibit color distortions due to the differences in realizable color gamuts and nonlinear characteristics of their components. In order to minimize color differences, it is desirable to apply color correction techniques. Th efirst step of color correction is to select the subset of the color coordinates representing the input color space. Th eselected subset serves as so called color samples to model the color distortion of a given color imaging device. The effectiveness of color correction is determined by the color sampels utilized in the modeling as well as the applied color correction technique. This paper presents a new selection method for color samples based on gentic algorithm. In the proposed method, structure of strings are designed so that the selected color samples fully represent the characteristics of color imaging device and consist of distinct color coordinates. To evaluate the performance of the selected color samples, they ar etuilized for three different color correction experiments. The experimentsal results are comapred with the crresponding results obtianed with the equally spaced color samples.

• IE interfaces
• /
• v.9 no.2
• /
• pp.19-37
• /
• 1996

자동차 도장공장의 마지막 도색공정인 상도공정에서는 도장할 차체의 색상(Color)이 직전에 도장된 차체의 색상과 다르면 스프레이 노즐에 남아있는 직전차체의 도료\를 세정하여 하는데, 이 때 도료손실과 세정비용 등의 색상변경비용(Color Change Cost)이 발생한다. 이러한 비용을 줄이기 위하여 동일한 색상의 차체들이 가능한 한 연속으로 도장될 수 있도록, 상도공정 직적에 동일한 차체들을 모은 저장창고(Color Grouping Buffer)가 필요하다. 본 논문에서는 도장공장의 상도공정에서의 색상변경비용을 줄일 수 있도록 저장창고에서의 차체의 인입, 저장, 인출을 실시간에 제어하는 Color Selection 시스템을 자동화하여 성공적으로 운영하고 있는 사례를 소개한다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.5
• /
• pp.889-898
• /
• 1997

Most general content-based image retrieval techniques use color and texture as retrieval indices. Spatial information is not used to color histogram and color pair based on color retrieval techniques. This paper proposes the selection of a set of representative in the duplicated color histogram, the analysis of spatial information of the selected colors and the image retrieval process based on the duplicated color histogram and spatial information. Two color historgrams for background and object are used in order to decide on color selection in the duplicated color histogram. Spatial information is obtained using a maximum entropy discretization. A retrieval process applies to duplicated color histogram and spatial to retrieve input images and relevant images. As the result of experiment of the image retrieval, improved color his togram and spatial information method hs increased the retrieval effectiveness more the color histogram method and color pair method.

• Journal of Korean Society of Rural Planning
• /
• v.16 no.3
• /
• pp.1-10
• /
• 2010

The purpose of this study is to find out the color preference on rural rooftop color. Today, public profit value of a rural community has been heavily recognized in the areas of preservation of pro-environmental and traditional life styles and foundation of collective community. Comparatively with urban, rural town conserves the scenic of those days when the historic landscape existed. Therefore, elements of historic and tradition in rural town are interesting resources to people who want traditional experience. Color is one of the most influenced elements for the image of Landscape. On the other hand, radical modernization has brought conflicting color element that does not blend with existing environmental color. Among others, roof represents one of the important traits of rapidly developing rural community due to vast amount of space it covers. In order to come up with more appropriate coloring scheme, it is necessary determine color that forms a balance with present conditions of rural life and historic landscape. This study provides more objective rooftop coloring selection process by employing additional surveys regarding color image adjective. I justified necessity of the balance between environmental color and roof color through analyzing correlation between environmental color of the rural town and Color Image Scale of the preliminary selection of roofs.

• Korean Institute of Interior Design Journal
• /
• no.27
• /
• pp.136-144
• /
• 2001

As various colors are used indoors and such colors influence on the image of indoors, color selection and color combination are a very important issue in inferior design. The purpose of this study is to analyse characteristic of color usage in interior design elements such as the floor, the wall, the ceiling and furnitures. The result of analysis shows the frequently used Munsell code corresponding to the cmyk code. Based on this analysis, this paper classifies largely into two kinds of the color combination type which can be used leer efficient color selection with good harmony The first combination type is divided into five types and the second is classified into three types. This paper argues that combination design principle, as a strong design tool, for color should be further developed for good quality of color design.

• Journal of Korea Multimedia Society
• /
• v.25 no.8
• /
• pp.1175-1187
• /
• 2022

3D interaction between humans and computers has been possible with the popularization of virtual reality, and it is important to study natural and efficient virtual reality user interfaces. In user interface development, it is essential to analyze and evaluate user factors. In order to analyze the influence of factors on users who use the virtual reality color picker, this paper divides the user groups based on whether they major in art or design, whether they have experience in virtual reality, and whether they have prior knowledge about 3D color space. The color selection error and color selection time of all user groups were compared and analyzed. Although there were statistically significant differences according to the user groups, all user groups used the virtual reality color picker accurately and effectively without any difficulties.

• The Research Journal of the Costume Culture
• /
• v.21 no.6
• /
• pp.938-949
• /
• 2013

This study aimed to provide the basic data of the establishment of marketing strategies by dividing consumer groups in accordance with the pursuit of clothing benefit, and then understanding the importance of clothing selection criteria in those groups, whether there are any differences in it between groups, and whether there are any differences in preference of clothing color depending on the mood state of those groups. The scale of this study was comprised of the pursuit of clothing benefit factors, clothing selection criteria factors, and the factors related to preference of clothing color by each mood state. In the results of the analysis, the factor most considered when male and female consumers in 20s~30s purchase clothing was fitting, and followed by convenience, stable shape, condition, design, and others' reaction in order. However, those 'design', 'convenience', 'others' reaction' and 'condition' factors were significantly different between groups. Therefore, the significance of this study is that fashion brands could develop new positioning maps for marketing and promotional strategies based on the pursuit of clothing benefit shown in this study.

• Korean Journal of Computational Design and Engineering
• /
• v.16 no.1
• /
• pp.61-72
• /
• 2011

As the customer's needs for diverse colors, the process of bus painting shop is becoming more and more complex. In particular, frequent changes of paint colors in each spray process require the cleaning of the painting nozzles and setting them up for the new paints, which results in increased time and cost and reduced production. This also increases environmental influences. This paper proposes, as a solution to this issue, the use of color selection field (CSF). CSF is physically a system of conveyors that are used to rearrange objects in a flow line. CSF is proposed, in this paper, to be introduced right before the spray process so that buses are better grouped according to their desired colors. Various parameters of the CSF, such as the number of conveyors and algorithms to determine the rearranged sequence of buses, have been determined by running simulations using the digital manufacturing technology, and investigating the simulation results. As an outcome of the proposed solution, the CSF system is expected to reduce approximately 30% of the nozzle cleaning cost for a Korean motor company case, which will not only benefit the company economically, but will also benefit the environment.

• International conference on construction engineering and project management
• /
• 2009.05a
• /
• pp.323-330
• /
• 2009

This paper presents the selection, examination, and user test (SEUT) procedure to determine the ideal color scheme for a 4D model. This systematic procedure can be performed iteratively to obtain the color scheme that would be most appropriate for construction purposes. To verify the proposed procedure, an example case with two iterations is presented. Ten color schemes were examined and 48 users tested during the two iterations, and the result shows that the SEUT procedure is an effective method for determining the ideal color scheme for 4D models.